GridCORTEX Live · Storm Workforce  ·  ← All Demos
On this page What you are watching The business case Run this at your utility Where you see it and how you say yes

The Second Night Synthetic Data · Simulation

Storms aren't won in hour three. They're won in hour thirty, when every crew is a human with a 16-hour clock, mutual assistance is arriving hungry and unfamiliar, and the dispatcher is making the same brutal call four hundred times: one more trouble call, or send them home? This is crew management from the control-center dispatcher's seat: 36 crews (native line, one-man service, tree, and two waves of mutual assistance) against 380 trouble orders, with hours-of-service, meals, fuel, materials, skill restrictions, and the relief wave that decides whether tomorrow exists. Watch the same storm hit the hour-16 wall without the math.

CREW
TYPE
STATUS / ASSIGNMENT
HOURS OF SERVICE
NOTES
Damage Map
Crew Board
06:00
STORM EXIT
⏳ DECISION POINT: TIME SLOWED
SYNTHETIC DATA
Primary out Transformer (T) ⚡ Wire down ▲ Tree on line Service call Bucket truck (line) Service van (1-man) Mutual assistance Tree crew + chipper ⛺ Staging (meals·fuel·materials)

Same storm. Two very different second nights.

What it's worth to treat crews as humans with limits, and logistics as math
,
Restoration (ETR)
,
HOS violations / safety
,
Customer-hours vs baseline
The Workforce
WithoutWith GridCORTEXΔ
The Event
WithoutWith GridCORTEXΔ
Illustrative simulation on synthetic data; crew counts, hours, and durations are placeholders. In a GridCORTEX pilot, the dispatch and fatigue models run on YOUR OMS history, YOUR union work rules, YOUR mutual assistance agreements, backtested against your last major storm. See UC 3.6 "Demo and Proof Plan."
96,400
Customers out
380
Open trouble orders
0 / 36
Crews in field / resting
0.0 h
Longest crew HOS right now
Dispatch Feed: OMS · AVL · crew radio · human-in-the-loop
06:00
Noon
18:00
Hour 16
06:00 D2
18:00 D2
The Validated Use Cases Behind This Scenario
UC 3.4
Crew Fatigue & Relief Modeling
Human limits as an optimization variable: who times out, who replaces them, and when to make the call, before the violation.
UC 3.6
AI Crew Dispatch & Routing
Damage, skills, truck equipment, travel time, and labor rules fused into one dispatch sequence, customers restored per crew-hour.
UC 3.8
Mutual Assistance Coordination
Crews drive 800 miles to help. This gets them from the parking lot to their first pole in 45 minutes, not half a day.
187 UCs
One Framework
The Second Night is one of 187 validated use cases across 10 solution areas and 23 utility domains.
Inside the Demo
What you are watching, and what it proves

The storm has just passed. It is 06:00 at the dispatch desk of a fictional utility, and the board shows 380 trouble orders, meaning individual repair jobs, with 96,400 customers without power. The workforce is 36 crews: 14 local two-person line crews, 6 one-person service crews restricted by rule to small jobs such as reconnecting individual homes, 4 tree-clearing crews, and 12 borrowed crews from other utilities, called mutual assistance, arriving in two waves at noon and at midnight. The simulation runs 36 hours, into the second night. One hard constraint shapes everything: safety rules cap each crew at 16 working hours, and a crew that hits the limit must stop, wherever it is. Storms are lost when every crew hits that wall at the same time.

Five decisions come to the dispatcher for approval. At 06:18 the first is counterintuitive: do not send all 24 local crews out at once. Hold five crews back as a fresh relief wave starting at 18:00, enforce a hard stop at 16 hours with a 30-minute buffer to get home, and schedule meals at hour 6 and refueling at hour 9. Otherwise the entire fleet times out in the same 90-minute window tonight, and restoration stops. At 07:12 the second decision places three staging sites, NORTHGATE YARD, RIVERSIDE FAIRGROUNDS, and BAYSHORE LOT, stocked with meals, fuel, and materials such as 12 spare transformers, wire, and poles, positioned where the damage actually is. That cuts wasted driving, called dead mileage, by a modeled 62 percent. Late morning, the third decision briefs the incoming borrowed crews while they are still on the road: local construction standards, sector maps, radio channels, a local buddy crew, and a first job already assigned. The first visiting crew is working on a pole 45 minutes after arriving, instead of losing half a day in a parking lot.

The centerpiece arrives at 19:36. Crew L-07 has worked 14.2 hours and just finished a job. The queue wants to hand them a 3-hour transformer replacement 35 minutes away, which would end at 18.1 hours on their clock, a safety violation. The software's answer: give them a 25-minute reconnection job 6 minutes off their route home, releasing them at 15.3 hours, and give the transformer job to crew M-04, which has 4.9 hours left and is 15 minutes closer. The dispatcher makes roughly 400 calls like this every storm, normally on gut feel alone. At 22:30 the fifth decision plans the second night: release the held relief crews, send the midnight wave of borrowed crews straight to staged work areas, and cycle the day-one crews back after full 10-hour rests, staggered so field coverage never drops below 60 percent.

On the approved path, the second night works instead of stalling. By hour 20, field coverage holds at 64 percent and the overnight backlog burns down from 190 open jobs to 120. Rested crews return from 04:00. The promised restoration time is met at 12:00 on day two as the last circuits come back. The borrowed crews go home a full day early. The event ends with zero work-hour violations, zero safety incidents, every meal on time, and the storm review file already assembled from the system's decision log. Total customer time without power comes in about 41 percent below the old way, roughly 1.2 million customer-hours instead of 2.1 million; a customer-hour is one customer dark for one hour.

Without GridCORTEX

The conventional storm sends everyone out at 06:00, so every crew's 16-hour clock expires between 22:00 and 23:30: the hour-16 wall, eleven crews timing out within 90 minutes, and restoration flatlining overnight near 200 open jobs. Meals are a 40-minute drive each way, so half the fleet skips them; every transformer job includes a 50-minute round trip to the yard for parts. The borrowed crews sit 4.6 hours in a parking lot waiting for orientation, and two are turned back because their equipment does not match local standards. At 14.9 hours on the clock, a fatigued crew backs a bucket truck into a pole stub: a near miss, a damaged truck, and a 40-minute fleet-wide stand-down. On day two, everyone returns at 08:00 into one fuel line and a scramble for materials. The result: 3 work-hour violations plus union grievances, the promised restoration time slips 14 hours to 20:00 on day two, and the state utility commission opens an inquiry into the storm response. The core failure: no system tracks human limits, so the dispatcher improvises 400 judgment calls alone.

With GridCORTEX

The change is treating crews as humans with limits, and logistics as math. The fatigue model staggers the crews' clocks at the start of the storm, so the hour-16 wall never forms (use case 3.4). The dispatch engine matches all 380 jobs to crew skills, truck equipment, travel time, and labor rules, including the route-home assignment that answers the one-more-call question with which job, not yes or no (use case 3.6). The mutual-assistance coordinator gets visiting crews from the parking lot to a pole in 45 minutes (use case 3.8). All five recommendations are approvals, not automation: the dispatcher approves each plan and crews confirm on the radio. The winning numbers: restoration promise met at 12:00 on day two, 14 hours faster; zero violations; zero incidents; customer time without power down 41 percent; wasted driving down 62 percent; and the borrowed crews released a day early, saving about $380,000.

The scorecard, side by side
MeasureWithout GridCORTEXWith GridCORTEXDelta
Hour-16 wallwhat happens when many crews hit the 16-hour work limit at the same time and restoration stops11 crews out in 90 mindesigned outstaggered clocks
HOS violationshours-of-service violations: times a crew was worked past the legal 16-hour safety limit3 + grievances0hard stops held
Fatigue near-missan exhausted crew's accident that almost hurt someone1: truck damagednonethe reason the math exists
MA time to first jobhow long borrowed mutual-assistance crews waited between arriving and starting useful work4.6 hours45 minonboarding done en route
One-man crew assignmentswhether one-person crews were sent only to jobs they are qualified and equipped to do2 sent to primary calls (turned back)service/patrol onlyskill rules enforced
Meals on timethe share of crews who actually got their scheduled meal breaks~55%: half skipped100% at staginghumans kept fueled
Dead mileagemiles driven that restore nothing, such as trips back to the yard for partsbaseline−62%supplies moved to the work
Restoration (ETR)the estimated time of restoration, the public promise of when the lights come back; D2 means day two20:00 D2: +14 hrs12:00 D2: met14 hours sooner
Customer-hourstotal outage suffering, counted as one customer dark for one hour~2.1M~1.2M41 percent less time dark
Overnight backlog burnwhether open repair jobs kept falling overnight, or froze when crews timed outfrozen ~200 orders190 → 120the second night worked
Crew utilizationthe share of paid crew hours spent actually repairing damage, rather than driving or waiting52% of paid hours on damage71%same fleet, more grid fixed
MA releasewhen the borrowed mutual-assistance crews, paid by the day, were sent homeheld an extra dayreleased a day earlyabout $380,000 saved
Storm review packetthe after-storm report; Relay is the system's decision log, which records every assignment as it happens3 weeks, from memoryRelay-traced, same weekregulator-ready
The dispatcher's nightthe roughly 400 assignment decisions one person makes per storm400 gut calls, alone400 computed calls, approvedthe human stays in charge
The live numbers on the dashboard
Customers outThe headline number, starting at 96,400. Falling steadily through the second night is success; a flat line overnight means the fleet has timed out.
Open trouble ordersThe live count of repair jobs against the initial 380. It grows as damage patrols find more work and shrinks as crews clear it; shrinking faster than it grows is what matters.
Crews in field / restingHow many crews are working versus resting. A healthy plan keeps the two in balance; a collapse to a handful of trucks at hour 16 means the storm is being lost.
Longest crew HOS right nowThe most tired crew's hours-of-service clock against the 16-hour legal limit. Green is fine; amber past 12 hours is a warning; red past 15 means that crew must be heading home.

The Business Case: Safety, Hours, and Cost

A utility does not buy a demo. It buys a safety exposure that goes away and a cost that goes down. Below is that case for every use case behind The Second Night, written the way a plant manager, a safety lead, and a CFO each need to read it. Every hour and every dollar is a formula you run with your own rates and volumes. There are no vendor benchmarks in here and no invented percentages. If a number is not yours, it is not a number.
UC 3.4 Crew Fatigue and Relief Modeling

What happens today, without this

By the second day of a major event, the emergency operations center (EOC) is tracking crew hours on a whiteboard, a spreadsheet, or in somebody's head. Someone works a phone list asking each crew how long they have been on, gets numbers that are already an hour stale, and tries to match them against the rest rules in the labor agreement. Relief decisions get made when a crew reports they are done, not before, and hours of service breaches usually surface weeks later when payroll reconciles the timesheets. The person doing this is a shift lead who should be running restoration.

What it replaces or shrinks

  • The whiteboard or spreadsheet of accumulated crew hours maintained by hand during an event
  • The phone round to each crew asking how long they have been working
  • Manual checking of each proposed relief against rest rules in the labor agreement
  • Shrinks the after event timesheet audit that currently finds hours of service breaches retroactively
  • The scramble to find a rested, correctly skilled crew once a time out has already happened
  • Hand projection of crew availability for the next operating period

Why it is safer

Fatigue in storm restoration is not an abstraction: it is a crew at hour fifteen working elevated on energized equipment and then driving home in the dark. The tool makes the time out visible hours before it arrives, so relief is scheduled rather than discovered, and nobody works past the limit because there was no one else to call.

Counted in units you already track:

  • Elevated work hours performed by crews past their hours of service limit
  • Night driving hours by crews driving back to lodging after an extended shift
  • Road miles driven by crews at the end of extended shifts
  • Switching operations performed by crews working past their rest rule limits

Man-hours it gives back

Storm room hours come back to the EOC shift lead and the storm room staff who currently spend the event tracking people instead of directing restoration.

HOURS AVOIDED PER YEAR = crews active in an event x hours per day the storm room spends tracking hours and calling crews divided by crews tracked per hour, x event days per year, plus post event timesheet audit hours per event x events per year, minus the shift lead's review time on each proposed relief plan.

The numbers we need from you to run that formula:

  • Crews active in a typical major event and event days per year over the last several years
  • Staff assigned to crew hour tracking during an event and hours per shift they spend on it
  • Hours spent auditing timesheets for hours of service breaches after each event
  • Hours of service and rest rules as written in your labor agreements, including the exceptions
  • Loaded hourly rates for EOC staff, a crew, and your overtime premium

Where the dollars come from

Cost driverHow it is calculated, from a rate you supply
Storm room labortracking hours avoided x your loaded EOC staff rate
Overtime premiumhours of avoidable overtime x your overtime premium rate, driven by relief that arrives on schedule instead of after a time out
Payroll and audit correctionpost event audit and correction hours avoided x your loaded payroll and labor relations rate
Incident and claim exposureyour own average cost of a fatigue related vehicle or field incident x the reduction you assume, a number you set from your own incident history
Grievance and dispute costyour own average cost to process a rest rule grievance x the number you believe scheduled relief prevents

Reliability and maintenance

Reliability
Restoration stalls when a crew times out mid job with no relief staged, so the effect is on restoration duration during major events. Note honestly that most of these hours fall on major event days that are excluded from your reported SAIDI (system average interruption duration index) under IEEE 1366, so measure this in customer minutes restored and in crew hours kept productive, not in your published reliability numbers.
Maintenance
The relevant effect is on handoff quality rather than on asset maintenance: a job handed from an exhausted crew to a rested one with a clean handoff note gets finished, while an abandoned partial job becomes tomorrow's rework and a second truck roll.

What else it moves

WorkforceRest rules in the labor agreement get honored because the system saw the limit coming, which is a different conversation with your union than an apology after the fact.
ComplianceYou end the event with a defensible hours of service record per crew, produced during the event rather than reconstructed from paper afterwards.
Insurance and riskDocumented fatigue management during extended events is a control your insurers ask about and that plaintiffs ask about after a storm related vehicle incident.

What it costs you, stated honestly

You pay for the GridCORTEX service, for integration with your OMS (outage management system) crew records and your timekeeping system, and for the work of encoding your actual rest rules, which are usually spread across multiple labor agreements and are rarely as simple as a single hour limit. That rules encoding is the real project cost, and it needs your labor relations people, not just IT.

How to build the payback case

Payback is usually driven by avoidable overtime and by storm room labor, since both come straight off your event cost reports. Incident and grievance avoidance are real but you should set those numbers yourself and keep them out of the base case.

This is a planning model built from your event history, your rest rules, and your rates, not a vendor claim. Re-run it after your first full storm season with the actual crew hours and overtime the model was meant to change.
UC 3.6 AI Crew Dispatch and Routing Optimizer

What happens today, without this

During a major event a storm dispatcher works from a damage list that keeps growing, a map, and their own memory of which crews are where, what is on each truck, and who is qualified for what. Assignments are made by radio, re-sequenced by radio, and rebuilt from scratch at every shift change when the next dispatcher inherits a list without the reasoning behind it. Whether a given sequence restored more customers per crew hour than another one is a question nobody can answer during the event, and usually not after it either.

What it replaces or shrinks

  • Hand sorting the trouble and damage list into an assignment order
  • The radio round to establish where each crew is and whether it is free
  • Manual matching of crew qualifications and truck equipment against each damage type
  • The whiteboard rebuild of the assignment plan at every shift change
  • Shrinks the post event reconstruction of what was assigned to whom and why
  • Hand recalculation of the plan every time a new priority job, such as a wire down, arrives

Why it is safer

The safety effect is mostly indirect and mostly about driving. Better sequencing removes crossing and backtracking miles during exactly the conditions where driving is most dangerous, at night, in weather, on roads with debris and downed conductors. There is a second effect that matters: a crew sent to a job its truck is equipped for is not improvising with the wrong equipment.

Counted in units you already track:

  • Road miles driven between jobs during an event
  • Night driving hours accumulated by crews being re-routed
  • Energized area entries by crews arriving without the correct equipment for the damage found
  • Switching operations performed out of sequence when restoration priorities are reworked by radio

Man-hours it gives back

Windshield hours come back to the crews and planning hours come back to the dispatchers, and both are hours you are already paying for at storm rates.

HOURS AVOIDED PER YEAR = crews x event days per year x hours per crew per day spent driving between jobs x the share of that driving the optimizer removes, which you set from a routing baseline, plus dispatchers per shift x shifts per event day x hours per shift building and rebuilding assignments x event days per year, minus dispatcher review time on each proposed sequence.

The numbers we need from you to run that formula:

  • Crews deployed in a typical event, including mutual aid, and event days per year
  • Hours per crew per day currently spent driving between jobs during an event
  • Dispatchers per shift and hours per shift spent constructing assignments
  • Damage points in a typical event and how often the plan is rebuilt
  • Loaded hourly rate for a crew, the mutual aid contracted day rate, and the loaded dispatcher rate

Where the dollars come from

Cost driverHow it is calculated, from a rate you supply
Crew productive timewindshield hours avoided x crew size x your loaded crew rate or the contracted mutual aid rate, whichever applies
Dispatcher laborplanning hours avoided x your loaded dispatcher rate
Fleet and fuelmiles avoided x your fleet cost per mile, applied across every truck in the event
Event durationcrew days removed from the event x your all in daily cost per crew, including lodging and per diem, which is where mutual aid gets expensive
Customer minutesyour own value per customer minute of interruption x the customer minutes restored earlier, a share you set from your own restoration curves

Reliability and maintenance

Reliability
The measure this actually moves is customers restored per crew hour and total restoration duration for the event. Note plainly that major event days are usually excluded from your reported SAIDI (system average interruption duration index) and SAIFI (system average interruption frequency index) under IEEE 1366, so the case should be argued in customer minutes and crew days, not in your published reliability statistics. Where it does show in public numbers is in your storm restoration commitments to your commission.
Maintenance
The lasting maintenance benefit is the record: a complete, timestamped account of which crew went where and what they found, which turns a storm into usable data about which parts of the system fail and how long they take to fix. That informs next year's hardening spend rather than evaporating at the end of the event.

What else it moves

CustomerFaster restoration for the same crew count, and a more defensible answer when a customer or an official asks why their street was not first.
ComplianceYour storm performance report to the commission is assembled from a real assignment record instead of reconstructed from radio logs and memory.
WorkforceDispatchers get to make judgment calls on priorities instead of doing combinatorial arithmetic on a whiteboard at hour thirty of a shift rotation.

What it costs you, stated honestly

You pay for the GridCORTEX optimization service, for integration into your OMS (outage management system) work queue and your automated vehicle location and crew qualification data, and for dispatcher training, because a dispatcher who does not trust the sequence will override it and you will get no benefit. Expect the crew qualification and truck equipment data to be the messiest input you own, and budget for cleaning it.

How to build the payback case

Payback is dominated by crew days removed from the event, especially contracted mutual aid crew days, because that is a rate you literally have an invoice for. Dispatcher labor is real but small next to it. Customer minutes are the largest number and the one to keep out of the base case.

This is a planning model built from your event history, your crew rates, and your restoration curves, not a vendor claim. Run it in shadow mode alongside your dispatchers for one event and re-run the model with what actually happened.
UC 3.8 Mutual Assistance Coordination Assistant

What happens today, without this

When mutual assistance is activated, a coordinator runs the event out of spreadsheets, email, and a phone. Crews from other utilities drive long distances, arrive in the middle of the night, and then wait, sometimes most of a day, for orientation to local safety rules, a work zone assignment, and lodging. Timesheets come in on paper from crews who do not use your systems and get re-keyed weeks later for cost recovery, which is when the disputes over hours and equipment rates start. The coordinator doing all of this is usually one person with a laptop who has not slept.

What it replaces or shrinks

  • Hand assembly of orientation packets covering your safety rules, radio channels, and lodging
  • The arrival roster spreadsheet maintained by phone as crews check in
  • Manual matching of arriving crews to work zones by equipment and qualification
  • Paper timesheet collection and re-keying into your cost system
  • Shrinks the post event reimbursement reconciliation with the assisting utilities
  • The repeated phone calls asking each crew where they are and when they will arrive

Why it is safer

A crew that has driven several hundred miles and then waits half a day is a fatigued crew starting late, and a crew released to work before it has absorbed your local rules is a crew operating on another utility's practices in your territory. Compressing orientation and getting assignments right at arrival is a safety control, not just a logistics improvement.

Counted in units you already track:

  • Night driving hours accumulated by arriving crews before they are stood down or assigned
  • Road miles driven by crews unfamiliar with the service territory searching for a work zone
  • Energized area entries by crews not yet oriented to your local safety rules and switching practice
  • Switching operations performed by crews accustomed to a different utility's procedures

Man-hours it gives back

The largest block of hours returned is not yours, it is the arriving crews' idle time between arrival and first assignment, and you are paying for those hours at a contracted rate.

HOURS AVOIDED PER YEAR = arriving crews x personnel per crew x hours between arrival and first productive assignment x the share of that wait the assistant removes, which you set, plus coordinators x hours per day on packets, rosters, and timesheets x event days, plus post event reconciliation hours per event, minus coordinator review time on packets and proposed assignments.

The numbers we need from you to run that formula:

  • Crews and personnel received in a typical activation, and activations per year
  • Hours between arrival and first assignment today, measured from your last event
  • Coordinators assigned during an activation and hours per day they spend on paperwork
  • Hours spent after the event reconciling timesheets and assembling the reimbursement package
  • Contracted hourly or daily rate for assisting crews, plus loaded rates for your coordinators and accounting staff

Where the dollars come from

Cost driverHow it is calculated, from a rate you supply
Idle crew timewait hours removed x personnel x the contracted rate you pay assisting crews, which you pay whether they are working or waiting
Coordinator laborcoordination hours avoided x your loaded coordinator rate, multiplied by the number of coordinators an activation consumes
Reconciliation and accountingpost event reconciliation hours avoided x your loaded accounting rate
Cost recovery exposureyour own history of disallowed or delayed storm cost recovery x the share you attribute to incomplete documentation, a number your regulatory accounting group already knows
Lodging and per diemcrew days removed from the event x your lodging and per diem cost per person per day

Reliability and maintenance

Reliability
Restoration duration during a major event is a function of productive crew hours on the ground, and hours spent waiting for orientation are hours not restoring customers. As with all major event work, note that these days are usually excluded from reported SAIDI (system average interruption duration index) under IEEE 1366, so measure this in customer minutes and in crew days, not in your published figures.
Maintenance
The durable effect is documentation quality rather than asset condition: a complete record of who worked what, with what equipment, and for how many hours, is what makes the next activation faster and the next rate filing defensible.

What else it moves

ComplianceStorm cost recovery filings live or die on documentation. Timesheets and assignment records assembled during the event, rather than reconstructed from paper afterwards, are the difference between a clean filing and a contested one.
CustomerEvery hour a crew spends waiting for a packet is an hour of customers still out, and those customers do not distinguish between your crews and the ones you borrowed.
WorkforceYour mutual assistance coordinator is the single most overloaded person in the event. This is the role most likely to burn out and hardest to backfill mid activation.

What it costs you, stated honestly

You pay for the GridCORTEX coordination assistant, for integration into your OMS (outage management system) work queue, your cost and timekeeping systems, and your email, and for your coordinators to keep the orientation content current, since your safety rules, radio channels, and lodging arrangements change between events. The content upkeep is small but it is not zero, and stale packets are worse than none.

How to build the payback case

Payback is dominated by idle crew hours at the contracted assisting rate, because that is the largest and best documented number in an activation. Coordinator labor and reconciliation are real but secondary, and cost recovery exposure should be sized by your regulatory accounting group, not by us.

This is a planning model built from your activation history, contracted rates, and measured wait times, not a vendor claim. Pull the arrival to assignment times from your last activation and re-run the model with those before you commit.
Each of these opens in full on the use case page, alongside the integration plan, the data ask, the path to production, and the operator console. Open the use case library.
For Your Architects and Data Owners
Run this at your utility

What is this, exactly? It is AI software: intelligent agents and models built and delivered by SoftServe, running on NVIDIA accelerated computing. It is not a hardware appliance and it does not replace the systems you run today. It deploys in your own cloud or on your premises, connects read-only to your existing systems, and recommends; your people approve every action, starting in shadow mode until it earns trust.

A decision support tool for the storm room: emergency operations center staff see a live board of each crew's accumulated hours, projected time-out, and the recommended relief crew and handoff time, with rest rules checked automatically. The demo above uses synthetic data; everything below describes what the real deployment needs from your organization.

Systems it connects to

Your systemTypical productsHow we connect
Field and crew systemsARCOS crew scheduling, mobile workforce tools, vehicle location (AVL)read-only API
Outage Management System (OMS)GE PowerOn, Oracle NMS, ADMS outage moduleread-only API
Time and labor systemUKG (Kronos), Workday, SAP time managementscheduled file export (CSV or CIM XML)
Weather and environmentNational Weather Service feeds, commercial forecast servicesread-only API
Geographic Information System (GIS)Esri ArcGIS Utility Network, GE Smallworldread-only API
Asset / work management (EAM/CMMS)IBM Maximo, SAP PM, Oracle WAMdatabase replica refreshed nightly
Document and knowledge storesSharePoint, safety briefing and orientation librariesdocument upload

Data it needs from you

How it runs on your systems

Runs in your cloud account on GPU instances or an on-premises NVIDIA server, read-only through your existing data zone, with no link to dispatch or control systems. It starts in shadow mode replaying past storms; relief calls remain human decisions.

Path to production

Weeks 1-3: data access and connection setup
Crew, timekeeping, and outage feeds connect read-only; your data access approvals set the pace.
Weeks 4-8: retrospective pilot
Your last major storm is replayed and the model's relief timing is compared with actual decisions and hours violations.
Weeks 9-10: evaluation and go or no-go
You decide with avoided violations and restoration impact quantified.
Months 3-5: production hardening
Security review, live feeds, monitoring, and storm room training, including one shadow-mode run in a real event.
Month 6 onward: in production
The emergency operations center works from the relief board in every major activation.

What we need from your team

Full integration, data, and timeline detail for each use case in this scenario: UC 3.4 · UC 3.6 · UC 3.8
For Your Operators and Dispatchers
Where you will see it and how you say yes

The Approve button you just clicked in the demo above is the real workflow. This is what it looks like on the screen of the emergency operations center shift lead in the GridCORTEX console:

GridCORTEX ConsoleSigned in: the emergency operations center shift lead
Notifications
Crew T-214 projected to hit 16-hour limit at 02:30; relief crew R-08 available for 01:45 handoff at Elm St staging
Daily model refresh complete; all connected feeds healthy
Recommendation
Relieve crew T-214 with R-08 at 01:45, before the hours-of-service limit
  • T-214 at 14.2 accumulated hours; projected time-out 02:30
  • R-08 rested 9 hours, 25 minutes from the handoff point
  • Rest rules check clean; the circuit job stays staffed
✓ Approve relief planModifyDecline
After you approve: The relief assignment posts to the crew system and the handoff logs in time and labor, and an audit entry records who approved it and why.
Computed from data as of 17:42:10 local; every card shows the timestamp of the data behind it.

What happens when you hit approve

Approving the relief flag does not block the crew in your OMS. GridCORTEX writes an advisory note to the crew record through the OMS API and alerts the dispatcher; your dispatch rules and the dispatcher decide the relief. Hard enforcement lives in your OMS, not in GridCORTEX.

How you tell it what it cannot see

The trigger is automatic from crew and time and labor feeds; no entry needed. If crew makeup changes in the field, the shift lead logs it in one click.

Live data, not stale data

Runs on live OMS assignments and time and labor clock data, refreshed every few minutes; each card shows its as-of timestamp, and pilot replicas show their cadence too.

Where it lives day to day

The GridCORTEX storm board beside the OMS; a crew within 4 hours of time-out pushes a mobile and Teams alert to the shift lead. The console runs in a browser beside your existing screens on day one; embedding into your own systems is a roadmap step once the read-only phase has earned trust. Approve, Modify, and Decline are all captured in an audit trail your compliance team can pull, and GridCORTEX never blocks or overrides anything in the systems you run today.

The Gap: Why Your Existing Systems Don't Already Do This

The fair question from any T&D ops leader: "We have an OMS, a workforce management system, AVL on every truck, and dispatchers who've run twenty storms, what's new here?" Here's the honest answer.

What you own keeps doing its job

  • OMS, remains the system of record for outages, nested calls, and restoration confirmation.
  • WMS / mobile workforce, work orders, timesheets, and crew mobile apps run as they do today.
  • AVL / GPS, truck positions keep flowing; they become an input, not a wall display.
  • Your dispatchers, every assignment you watched was approved from the dispatcher's seat. The judgment stays human.

The gap GridCORTEX fills, above them, not instead of them

  • The OMS knows outages. Nothing knows humans. Hours-of-service lives in a spreadsheet updated between radio calls. By hour 30, "who is about to time out and who replaces them" is the entire game, and no system computes it.
  • The "one more call" decision has no math today. A tired dispatcher decides 400 times per storm whether a 14.5-hour crew takes one more job. The right answer is usually neither yes nor no, it's WHICH job: the 25-minute service restore on their route home, never the 3-hour transformer 40 minutes out.
  • WMS schedules blue-sky work. Storm dispatch (skills, truck equipment, one-man restrictions, travel, staged materials, labor rules, 380 orders) is a routing optimization your WMS was never built to solve, recomputed every time the picture changes.
  • Logistics is somebody's clipboard. Meals, fuel, and material pods placed by math against where the work actually is cut dead mileage ~60%, that's field hours, not comfort.
  • Mutual assistance arrives blind. Orientation, standards familiarization, sector assignment, buddy pairing, done en route and pre-staged, not in a parking lot for half a day.
Accent, don't replace: GridCORTEX reads your OMS, WMS, AVL, and crew rosters · computes fatigue, dispatch, and logistics above them · and hands every assignment to your dispatchers to approve. The crews get home safe. The ETR holds. And the second night is just a night shift.
Under the Hood: What GridCORTEX Took Into Account in This Scenario

When someone asks "what did it actually calculate?", this is the list. In the simulation these factors drive the storyline; in a pilot they are computed from your OMS history, work rules, and mutual assistance agreements.

⏱ The Human Model

  • Per-crew hours-of-service clock with the 16-hour limit, meal/rest requirements, and a return-travel buffer, nobody stranded at 15:55 forty minutes from home
  • Shift staggering at storm entry so the whole fleet doesn't expire in the same hour, the hour-16 wall designed out before it forms
  • Relief-wave planning: crews held back, rest cycles tracked, day-two coverage protected while day one still rages
  • Fatigue-aware assignment: complex primary work early in a shift, simpler calls late

🚚 The Dispatch Model

  • Skill and equipment matching: one-man service crews get service drops, single-outs, and patrols, never primary conductor or transformer work
  • Tree crews sequenced ahead of line crews where vegetation blocks access
  • Routing optimization (cuOpt-class) across 380 orders: customers restored per crew-hour, critical loads weighted, travel minimized
  • The route-home assignment: last calls chosen so the drive home does useful work

⛺ The Logistics Model

  • Forward staging placement against the damage map: meals, fuel bowsers, and material pods (transformers, wire, poles) where the work is
  • Material availability fused into job estimates; the 50-minute yard run priced into every assignment, then eliminated
  • Fuel rotations scheduled off-peak so trucks never queue

🤝 Mutual Assistance & The Record

  • Arriving waves oriented en route: standards packets, sector maps, buddy assignments, first jobs pre-staged (UC 3.2 briefs in the cab)
  • MA release timing computed; a day of 12 foreign crews you don't need is real money
  • Every assignment and HOS decision Relay-traced: the storm review and the regulator's crew-utilization questions answered from the log
  • Runs always-on via the NVIDIA Agent Toolkit, the model watched the forecast and drafted the stagger plan before landfall

Presenter's one-liner: "Every crew is a 16-hour clock. The system staggered the clocks, put meals and transformers where the work was, got mutual assistance from the parking lot to a pole in 45 minutes, answered the one-more-call question four hundred times with math, and the second night was just a night shift. Same storm, fourteen hours faster, everyone home safe."

GridCORTEX Live Scenario Demo · Synthetic data throughout, no utility, crew, or actual event is depicted · GridCORTEX recommends; dispatchers assign and crews confirm · SoftServe + NVIDIA · Created by Ronnie Mauldin, NVIDIA Solutions Director, Power & Utilities, SoftServe · JUL 2026